JFE has filed a patent for a method of predicting hydrogen content in steel strips in a continuous galvanizing line. The method involves acquiring input data from operation parameters and transformation rate information, and using a machine learning prediction model to determine the hydrogen content downstream of the reheating process. GlobalData’s report on JFE gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on JFE, polymer electrolyte fuel cells was a key innovation area identified from patents. JFE's grant share as of September 2023 was 38%. Grant share is based on the ratio of number of grants to total number of patents.
Method of predicting hydrogen content in steel strip downstream of reheating process
A recently filed patent (Publication Number: US20230313355A1) describes a method for predicting and controlling hydrogen content in steel strips in a continuous galvanizing line. The method involves acquiring input data, such as operation parameters and transformation rate information, and using a machine learning prediction model to estimate the hydrogen content downstream of the reheating process.
The patent claims that the method can further include acquiring attribute parameters related to the chemical composition of the steel strip as input data. This additional information may enhance the accuracy of the hydrogen content prediction.
Furthermore, the patent describes a method for controlling the hydrogen content in steel strips. If the predicted hydrogen content exceeds a preset upper limit, the method suggests resetting operation parameters of the continuous galvanizing line to ensure the hydrogen content remains within the desired range.
The patent also covers a method for manufacturing steel strips using the prediction model. The method involves acquiring operation parameters and transformation rate information as input data, predicting the hydrogen content using the machine learning model, and resetting operation parameters if necessary to maintain the desired hydrogen content.
Additionally, the patent describes a method for forming the prediction model itself. This involves acquiring operational performance data and training data, where the information on hydrogen content in steel is used as output performance data. The prediction model is then developed using machine learning techniques such as neural networks, decision tree learning, random forest, or support vector regression.
The patent also includes a device that predicts hydrogen content in steel strips. The device consists of an acquisition unit that acquires operation parameters and transformation rate information, and a prediction unit that uses the trained prediction model to estimate the hydrogen content downstream of the reheating process.
The device can be connected to a terminal device with an input unit and a display unit. The acquisition unit can update operation parameters based on user input, and the display unit can show the predicted hydrogen content using the updated parameters.
In summary, this patent presents a method and device for predicting and controlling hydrogen content in steel strips in a continuous galvanizing line. The use of machine learning and various input parameters allows for accurate predictions and potential adjustments to maintain the desired hydrogen content.
To know more about GlobalData’s detailed insights on JFE, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies
